2019/09/07 by Georgios Papagiannis, Papagiannis, Georgios, Sotiris Moschoyiannis +1
Biochemistry, Genetics and Molecular Biology · Psychology · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #FOS: Electrical engineering #Gene Regulatory Network Analysis #Machine Learning (cs.LG) #Mental Health Research Topics #Receptor Mechanisms and Signaling #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1909.03331
openalex publication_date 2019/09/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Probabilistic Boolean Networks (PBNs) were introduced as a computational\nmodel for the study of complex dynamical systems, such as Gene Regulatory\nNetworks (GRNs). Controllability in this context is the process of making\nstrategic interventions to the state of a network in order to drive it towards\nsome other state that exhibits favourable biological properties. In this paper\nwe study the ability of a Double Deep Q-Network with Prioritized Experience\nReplay in learning control strategies within a finite number of time steps that\ndrive a PBN towards a target state, typically an attractor. The control method\nis model-free and does not require knowledge of the network's underlying\ndynamics, making it suitable for applications where inference of such dynamics\nis intractable. We present extensive experiment results on two synthetic PBNs\nand the PBN model constructed directly from gene-expression data of a study on\nmetastatic-melanoma.\n